© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26382
    Prev
    Next
    INDEX
    Explanations

    positive numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plash
    -0.08
    ippe
    -0.08
    åĩłæĿ¡
    -0.07
    entie
    -0.07
    åģ¶å°Ķ
    -0.07
     Appel
    -0.07
    åħį
    -0.07
    ç¼Ģ
    -0.07
    %p
    -0.07
    caller
    -0.06
    POSITIVE LOGITS
     positive
    0.16
     Positive
    0.14
    _positive
    0.14
    positive
    0.14
    Positive
    0.13
     positively
    0.12
    -positive
    0.12
     pozitiv
    0.12
     positiva
    0.12
    为æŃ£
    0.11
    Activations Density 0.038%

    No Known Activations